centos7 + hadoop 2.7.7 完全分布式搭建

[root@hadoop0 ~]# vi /etc/hosts
配置主机host
127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4
::1 localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.100.21 hadoop0
192.168.100.22 hadoop1
192.168.100.23 hadoop2
将配置发送到其他主机（同时在其他主机上配置）
[root@hadoop0 ~]# scp -r /etc/hosts root@hadoop1:/etc/
[root@hadoop0 ~]# scp -r /etc/hosts root@hadoop2:/etc/
测试
[root@hadoop0 ~]# ping hadoop0
[root@hadoop0 ~]# ping hadoop1
[root@hadoop0 ~]# ping hadoop2

在所有的主机下均建立一个账号hadoop用来运行hadoop ，并将其添加至sudoers中
[root@hadoop0 ~]# useradd hadoop    #添加用户通过手动输入修改密码
[root@hadoop0 ~]# passwd  hadoop    #更改用户 hadoop 的密码
hadoop  #密码
#passwd： 所有的身份验证令牌已经成功更新。
设置hadoop用户具有root权限  修改 /etc/sudoers 文件，找到下面一行，在root下面添加一行，如下所示：
[root@hadoop0 ~]# vim /etc/sudoers

#找到这里
## Allow root to run any commands anywhere
root    ALL=(ALL)     ALL
hadoop   ALL=(ALL)     ALL

修改完毕  ：wq！ 保存退出，现在可以用hadoop帐号登录，然后用命令 su hadoop ，切换用户即可获得root权限进行操作。　

1）在root用户下创建hadoop文件夹
[root@hadoop0 /]# cd /
[root@hadoop0 /]# mkdir hadoop
2）修改hadoop文件夹的所有者
[root@hadoop0 opt]# chown -R hadoop:hadoop /hadoop
3）查看hadoop文件夹的所有者
[root@hadoop0 /]# ll

  drwxr-xr-x. 4 hadoop hadoop 46 May 10 16:56 hadoop

[root@hadoop0 ~]# rpm -qa|grep java   #查询是否安装java软件：
这里使用官网下载好的tar包传到服务器  /hadoop 下 
[root@hadoop0 hadoop]# tar -zxvf  jdk-8u181-linux-x64.tar.gz 
[root@hadoop0 hadoop]# mv jdk1.8.0_181 jdk1.8
设置JAVA_HOME

[root@hadoop0 hadoop]# vim /etc/profile

#在文件末尾添加

#JAVA
export JAVA_HOME=/hadoop/jdk1.8
export JRE_HOME=/hadoop/jdk1.8/jre
export CLASSPATH=.:$CLASSPATH:$JAVA_HOME/lib:$JRE_HOME/lib
export PATH=$PATH:$JAVA_HOME/bin:$JAVA_HOME/sbin

[root@hadoop0 hadoop]# source /etc/profile  #重启配置文件生效
#检查是否配置成功

[hadoop@hadoop0 /]$ java -version
java version "1.8.0_181"
Java(TM) SE Runtime Environment (build 1.8.0_181-b13)
Java HotSpot(TM) 64-Bit Server VM (build 25.181-b13, mixed mode)

[hadoop@hadoop0 ~]# ssh-keygen -t rsa
[hadoop@hadoop0 ~]# ssh-copy-id hadoop0
[hadoop@hadoop0 ~]# ssh-copy-id hadoop1
[hadoop@hadoop0 ~]# ssh-copy-id hadoop2

[hadoop@hadoop1 ~]# ssh-keygen -t rsa
[hadoop@hadoop1 ~]# ssh-copy-id hadoop1
[hadoop@hadoop1 ~]# ssh-copy-id hadoop0
[hadoop@hadoop1 ~]# ssh-copy-id hadoop2

[hadoop@hadoop2 ~]# ssh-keygen -t rsa
[hadoop@hadoop2 ~]# ssh-copy-id hadoop2
[hadoop@hadoop2 ~]# ssh-copy-id hadoop0
[hadoop@hadoop2 ~]# ssh-copy-id hadoop1　

[hadoop@hadoop0 hadoop]# tar -zxvf hadoop-2.7.7.tar.gz

[hadoop@hadoop0 hadoop]$ vi core-site.xml
<configuration>

<!-- 指定HDFS中NameNode的地址 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoop0:9000</value>
</property>
<!-- 指定hadoop运行时产生文件的存储目录,注意tmp目录需要创建 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/hadoop/hadoop-2.7.7/tmp</value>
</property>

</configuration>

[hadoop@hadoop0  hadoop]$ vi hadoop-env.sh 
修改 export JAVA_HOME=/hadoop/jdk1.8

[hadoop@hadoop0  hadoop]$ vi hdfs-site.xml
<configuration>

<!-- 设置dfs副本数，不设置默认是3个 -->
<property>
<name>dfs.replication</name>
<value>2</value>
</property>

<!-- 设置namenode数据存放路径 -->
<property>
<name>dfs.name.dir</name>

<value>/hadoop/hadoop-2.7.7/dfs/name</value>

</property>

<!-- 设置datanode数据存放路径 -->
<property>

<name>dfs.data.dir</name>

<value>/hadoop/hadoop-2.7.7/dfs/data</value>

</property>
<!-- 设置secondname的端口 -->
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hadoop1:50090</value>
</property>

</configuration>

[hadoop@hadoop0  hadoop]$ vi slaves
hadoop0
hadoop1
hadoop2

[hadoop@hadoop0 hadoop]# mv mapred-site.xml.template mapred-site.xml
[hadoop@hadoop0 hadoop]$ vi mapred-site.xml
<configuration>
<!-- 指定mr运行在yarn上 -->
    <property>
     <name>mapreduce.framework.name</name>
     <value>yarn</value>
    </property>
</configuration>

[hadoop@hadoop0 hadoop]$ vi yarn-site.xml
<configuration>
<!-- reducer获取数据的方式 -->
     <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
     </property>
<!-- 指定YARN的ResourceManager的地址 -->
     <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop0</value>
     </property>
</configuration>

[hadoop@hadoop0 /]# scp -r hadoop/ hadoop@hadoop1:$PWD
[hadoop@hadoop0 /]# scp -r hadoop/ hadoop@hadoop2:$PWD

[hadoop@hadoop0 ~]$ sudo vim /etc/profile
末尾追加
export  HADOOP_HOME=/hadoop/hadoop-2.7.7
export  PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
编译生效  source  /etc/profile

[hadoop@hadoop0 hadoop-2.7.7]$ hdfs namenode -format　

[hadoop@hadoop0 ~]# start-dfs.sh

Starting namenodes on [hadoop0]
hadoop0: starting namenode, logging to /hadoop/hadoop-2.7.7/logs/hadoop-hadoop-namenode-hadoop0.out
hadoop0: starting datanode, logging to /hadoop/hadoop-2.7.7/logs/hadoop-hadoop-datanode-hadoop0.out
hadoop2: starting datanode, logging to /hadoop/hadoop-2.7.7/logs/hadoop-hadoop-datanode-hadoop2.out
hadoop1: starting datanode, logging to /hadoop/hadoop-2.7.7/logs/hadoop-hadoop-datanode-hadoop1.out
Starting secondary namenodes [hadoop1]
hadoop1: starting secondarynamenode, logging to /hadoop/hadoop-2.7.7/logs/hadoop-hadoop-secondarynamenode-hadoop1.out

[hadoop@hadoop1 ~]# start-yarn.sh

starting yarn daemons
starting resourcemanager, logging to /hadoop/hadoop-2.7.7/logs/yarn-hadoop-resourcemanager-hadoop0.out
hadoop2: starting nodemanager, logging to /hadoop/hadoop-2.7.7/logs/yarn-hadoop-nodemanager-hadoop2.out
hadoop1: starting nodemanager, logging to /hadoop/hadoop-2.7.7/logs/yarn-hadoop-nodemanager-hadoop1.out
hadoop0: starting nodemanager, logging to /hadoop/hadoop-2.7.7/logs/yarn-hadoop-nodemanager-hadoop0.out

[hadoop@hadoop0 hadoop-2.7.7]$ jps
2162 NodeManager
2058 ResourceManager
2458 Jps
1692 NameNode
1820 DataNode

[hadoop@hadoop1 hadoop]$ jps
1650 Jps
1379 DataNode
1478 SecondaryNameNode
1549 NodeManager

[hadoop@hadoop2 hadoop]$ jps
1506 DataNode
1611 NodeManager
1711 Jps

1）各个服务组件逐一启动
分别启动hdfs组件： hadoop-daemon.sh  start|stop  namenode|datanode|secondarynamenode
   启动yarn：     yarn-daemon.sh    start|stop  resourcemanager|nodemanager

2）各个模块分开启动（配置ssh是前提）常用
start|stop-dfs.sh     start|stop-yarn.sh

3）全部启动（不建议使用）
start|stop-all.sh

[hadoop@hadoop0 hadoop-2.7.7]$ ntp

bash: ntp: command not found

[hadoop@hadoop0 hadoop-2.7.7]$ sudo yum install ntp #安装ntp

[hadoop@hadoop0 hadoop-2.7.7]$ sudo ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime   #linux的时区设置为中国上海时区

[hadoop@hadoop0 hadoop-2.7.7]$ sudo ntpdate time.windows.com #与当地网络时间同步
12 May 12:33:09 ntpdate[2571]: adjust time server 13.70.22.122 offset 0.029582 sec
[hadoop@hadoop0 hadoop-2.7.7]$ date #查看是否同步成功
Sun May 12 12:33:16 CST 2019